Evaluation of Key Parameters Using Deep Convolutional Neural Networks for Airborne Pollution (PM10) Prediction

Table 13

Three best models of 2CNN architectures.

Architecture	Activation function	First kernel size	Second kernel size	RMSE	MAPE	IOA	R^2
CNN	Linear	20	3	19.2497	0.2314	0.8704	0.6079
		50	3	19.3115	0.2338	0.8729	0.6053
		50	6	19.2326	0.2317	0.8747	0.6086